LINKED LIST [txt mode] ▸ [Spec Decode] Add Gemma4 MTP speculat...
home explore | log in

[Spec Decode] Add Gemma4 MTP speculative decoding support by lucianommartins · Pull Request #41745 · vllm-project/vllm

github.com · 2026-09-25 · 0 upvotes

log in to save, upvote or flag this.


─── In 0 lists ─────────────────────────────────────────

(not in any lists yet)

* Accelerating Gemma 4: faster inference with multi-token prediction drafters (from the discussion)